Proactive Analytics is now ⚡ Proactive Agents

One of the things we hear most from teams running Proactive Analytics is simple: "The scheduled write-ups are great, but I do not want one more thing to check. I want to hear from Zoë only when something actually needs me." Starting today, you can. Proactive Analytics is now Proactive Agents, and here is what changed:

• Conditional alerts with intelligent thresholds. Tell an agent what "worth my attention" means, and Zoë only reaches out when the line is crossed. Below the threshold, she stays quiet, so you get signal, not noise.
• The root cause, already found. Every delivery is a deep-dive analysis with the driver identified, not just a number that moved.
• Context that stays current. Agents sync context across your org through your MCP connectors, so the data model behind every run keeps up with your business.

Building one takes a minute. Give a person or agent what it needs across three steps:

• Instructions: Write what you want in plain English, for example "Check if daily revenue dropped more than 5% versus the last completed business day, and if so find the root cause."
• Triggers and tools: Put it on a schedule and choose what it can use, from Web Search to Edit Data Model to your MCP connectors.
• Delivery: Decide who gets results and how, and include a shared chat link so the team can pick up right where Zoë left off.

What happens to your existing Proactive Analytics:

• Every Proactive Analytics schedule you already set up has been converted to a Proactive Agent automatically.
• Your agents keep running on the same cadence, at the same times, delivered to the same people.
• There is nothing to rebuild or reconfigure. Open any converted agent whenever you want to add a threshold, tools, or connectors.
• You will now find everything under the ⚡ Proactive Agents section in the left sidebar.

Full details are in our Proactive Agents docs